The Opus 4.8 number nobody's posting Not the coding score. Plus Open Design at 4 weeks, and 2 more reads. The Opus 4.8 number nobody's posting Hey Reader, Anthropic shipped Claude Opus 4.8 this week, and the whole feed posted the same screenshot – the coding score. That's the least interesting part. The number that actually changes how you work is below, plus three more reads stacked behind it. Claude Opus 4.8 – the number nobody's posting Everyone screenshotted the coding score (64.3% to...
1 day ago • 2 min read
Should AI write your code unsupervised? My answer + today's source-control post. Plus 2.1.141 and Episode 2. Should AI write your code unsupervised? Hey Reader, Short answer to the subject line: yes – but only with the workflow underneath. "Unsupervised" doesn't mean nobody's reviewing, it means the human moves from typing to reviewing. The three reads below are the layers of that workflow stack. Plan Mode is how you organize a session before the agent runs. Source control is the safety net...
15 days ago • 3 min read
Claude Code's limits just doubled Plus the silent 1-hour cache bug in 2.1.131, Episode 2 of the production series, and every WotAI live session now on YouTube. Claude Code's limits just doubled Hey Reader, Eight days, four posts. Big week for Claude Code: 5-hour rate limits doubled (and Anthropic signed for an entire SpaceX data center to back it up), 2.1.131 quietly fixed a 1-hour prompt-cache bug that had been silently overcharging anyone running long-TTL cache control, Episode 2 of the...
22 days ago • 3 min read
I'm running a Claude Code workshop in June Production-Grade Claude Code in 5 Days, plus a drawing for 10 free seats from the community. I'm running a Claude Code workshop in June Quick note. I'm running a workshop in June called Production-Grade Claude Code in 5 Days. Five live sessions on the parts of Claude Code most people never reach for, but where the actual value lives. Here's what we cover. 📐 Day 1 is CLAUDE.md architecture. Most CLAUDE.md files are walls of text that Claude ignores....
23 days ago • 1 min read
I rewrote my CLAUDE.md this week Plus the 1M context bill, an 11-day design-tool fork, and the release that survives Mac sleep. I rewrote my CLAUDE.md this week Hey Reader, Two weeks since the last email. A lot happened. The thread that ties it all together: Opus 4.7 dropped on April 17, and almost every Claude Code release since has been about hardening the runtime around the new model. Memory leaks, context calculation, OAuth resilience, Mac-sleep recovery, managed settings, gateway...
29 days ago • 3 min read
Claude Code week – Opus 4.7, routines, and multi-agent review Four posts on what changed in Claude Code this week (plus Opus 4.7 benchmarks). Claude Code week – Opus 4.7, routines, and multi-agent review Hey Reader, Four posts on Claude Code, all connected. Anthropic shipped Opus 4.7 on Thursday, Claude Code 2.1.112 on Friday, and the thread running through every release this month is the same – make the agent loop tighter. Here's the reading order I'd suggest. Claude Opus 4.7 + Claude Code...
about 1 month ago • 2 min read
This week on the blog Plus: n8n security audit checklist, visual diff tutorial, and webhook debugging cheat sheet. This week on the blog Four posts this week – two new, two you might have missed. What is agent washing? Most “AI agent” products are deterministic workflows with an LLM classifier on top. There’s nothing wrong with that – unless you’re lying about it. Why your n8n workflows might be more honest than most vendor demos. Read the agent washing breakdown → n8n security audit...
about 2 months ago • 1 min read
I built the thing I wished existed when building n8n workflows Describe what you want. Get valid JSON out. No hallucinated nodes. I built the thing I wished existed when building n8n workflows Hey Reader, You're on this list because you either bought one of my n8n workflows or signed up for n8n through my link – either way, you're building automations and I've got something new for you. You already know the pain – building a workflow from scratch takes hours. Configuring nodes, debugging...
about 2 months ago • 1 min read
